1·The delta rule is based on the idea of gradient descent.
而delta规则是基于梯度降落这样一种思路。
2·BP neural network, as its nature of gradient descent method, is easy to fall into local optimum.
但BP神经网络本质是梯度下降法，容易陷入局部最优。
3·However, BP network with gradient descent has some defects such as low convergence speed, fall in local minima.
然而基于梯度下降的BP网络存在收敛速度慢、易陷入局部极小的缺陷。
4·This paper studies BP network, realizes the method of gradient descent, gets better result than traditional one.
本文研究了BP网络，实现了“梯度下降法”的网络训练方法，获得了较传统方法好的效果。
5·Gradient descent algorithm is an efficient method to train FNN, and it can be realized in batch or incremental manner.
梯度下降算法是训练多层前向神经网络的一种有效方法，该算法可以以增量或者批量两种学习方式实现。
6·The weights are trained with Gradient Descent Method. The increase algorithm of BVS, and restricted algorithm, was induced.
利用梯度下降法对网络的权值进行训练，并且推导了BVS的增长算法，以及网络训练的限制记忆递推公式。
7·The model was a Feedforward Fuzzy neural network possessing five layers, and Gradient Descent was adopted as learning algorithm.
该模型采用五层前向模糊神经网络，学习算法为梯度下降法。
8·A few or all of the parameters of the controller are adjusted by using the gradient descent algorithm to minimize the output error.
运用最优梯度下降法使目标的计算值与期望值误差最小来迭代优选权重，建立迭代算法模型。
9·Two ways are used to design the network, the one is the direct energy descent method, and the other is the gradient descent method.
有两种方法可以用来设计网络，一是能量下降法，另一个是梯度下降法。
10·This paper researches the application of the stochastic parallel gradient descent (SPGD) optimization algorithm on the beam cleanup system.
就随机并行梯度下降(SPGD)最优化算法在光束净化系统中的应用展开研究。